{"total":206,"rows":[{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111,"area":"agents"},{"id":"2510.25726","title":"The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution","created":"2025-10-29","cited_by_count":85,"area":"agents"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"area":"agents"},{"id":"2603.02176","title":"Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale","created":"2026-03-02","cited_by_count":72,"area":"agents"},{"id":"2604.06132","title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","created":"2026-04-07","cited_by_count":64,"area":"agents"},{"id":"2506.01716","title":"Self-Challenging Language Model Agents","created":"2025-06-02","cited_by_count":59,"area":"agents"},{"id":"2508.09124","title":"OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows","created":"2025-08-12","cited_by_count":57,"area":"agents"},{"id":"2505.18878","title":"CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions","created":"2025-05-24","cited_by_count":47,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2505.21936","title":"RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments","created":"2025-05-28","cited_by_count":46,"area":"agents"},{"id":"2506.14205","title":"AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents","created":"2025-06-17","cited_by_count":46,"area":"agents"},{"id":"2504.11543","title":"REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites","created":"2025-04-15","cited_by_count":45,"area":"agents"},{"id":"2601.17087","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","created":"2026-01-23","cited_by_count":40,"area":"agents"},{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2502.13069","title":"Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering","created":"2025-02-18","cited_by_count":38,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2504.14064","title":"DoomArena: A framework for Testing AI Agents Against Evolving Security Threats","created":"2025-04-18","cited_by_count":32,"area":"agents"},{"id":"2503.07919","title":"BEARCUBS: A benchmark for computer-using web agents","created":"2025-03-10","cited_by_count":31,"area":"agents"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2506.01952","title":"WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks","created":"2025-06-02","cited_by_count":30,"area":"agents"},{"id":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30,"area":"agents"},{"id":"2603.00718","title":"SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?","created":"2026-02-28","cited_by_count":30,"area":"agents"},{"id":"2605.03596","title":"Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies","created":"2026-05-05","cited_by_count":29,"area":"agents"},{"id":"2604.09408","title":"HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?","created":"2026-04-10","cited_by_count":27,"area":"agents"},{"id":"2511.05269","title":"TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems","created":"2025-11-07","cited_by_count":26,"area":"agents"},{"id":"2505.21116","title":"Creativity in LLM-based Multi-Agent Systems: A Survey","created":"2025-05-27","cited_by_count":23,"area":"agents"},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2604.24964","title":"Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks","created":"2026-04-27","cited_by_count":21,"area":"agents"},{"id":"2605.02240","title":"PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments","created":"2026-05-04","cited_by_count":21,"area":"agents"},{"id":"2505.18646","title":"SEW: Self-Evolving Agentic Workflows for Automated Code Generation","created":"2025-05-24","cited_by_count":20,"area":"agents"},{"id":"2506.06299","title":"How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare","created":"2025-05-18","cited_by_count":20,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2507.04103","title":"How to Train Your LLM Web Agent: A Statistical Diagnosis","created":"2025-07-05","cited_by_count":19,"area":"agents"},{"id":"2509.10397","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","created":"2025-09-12","cited_by_count":19,"area":"agents"},{"id":"2605.12015","title":"SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces","created":"2026-05-12","cited_by_count":19,"area":"agents"},{"id":"2506.22598","title":"RExBench: Can coding agents autonomously implement AI research extensions?","created":"2025-06-27","cited_by_count":18,"area":"agents"},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"area":"agents"},{"id":"2510.27287","title":"Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments","created":"2025-10-31","cited_by_count":17,"area":"agents"},{"id":"2604.23781","title":"ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents","created":"2026-04-26","cited_by_count":17,"area":"agents"},{"id":"2607.10059","title":"AgentAbstain: Do LLM Agents Know When Not to Act?","created":"2026-07-11","cited_by_count":17,"area":"agents"},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16,"area":"agents"},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"area":"agents"},{"id":"2506.00073","title":"The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets","created":"2025-05-29","cited_by_count":15,"area":"agents"},{"id":"2506.03828","title":"AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance","created":"2025-06-04","cited_by_count":15,"area":"agents"},{"id":"2603.13594","title":"EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings","created":"2026-03-13","cited_by_count":15,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2604.28139","title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","created":"2026-04-30","cited_by_count":13,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2509.25609","title":"A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments","created":"2025-09-30","cited_by_count":12,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2603.10505","title":"Safe and Scalable Web Agent Learning via Recreated Websites","created":"2026-03-11","cited_by_count":11,"area":"agents"},{"id":"2604.01212","title":"$\\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution","created":"2026-04-01","cited_by_count":11,"area":"agents"},{"id":"2605.14271","title":"Auditing Agent Harness Safety","created":"2026-05-14","cited_by_count":11,"area":"agents"},{"id":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"id":"2505.09757","title":"Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agents","created":"2025-05-14","cited_by_count":10,"area":"agents"},{"id":"2508.04026","title":"VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking","created":"2025-08-06","cited_by_count":10,"area":"agents"},{"id":"2604.13072","title":"LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks","created":"2026-03-20","cited_by_count":10,"area":"agents"},{"id":"2607.02294","title":"Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions","created":"2026-07-02","cited_by_count":10,"area":"agents"},{"id":"2607.23809","title":"ACM: Agentic Context Management for Long Horizon Tasks","created":"2026-07-26","cited_by_count":10,"area":"agents"},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2602.16179","title":"EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments","created":"2026-02-18","cited_by_count":8,"area":"agents"},{"id":"2606.03135","title":"Uncertainty-Aware Clarification in LLM Agents with Information Gain","created":"2026-06-02","cited_by_count":8,"area":"agents"},{"id":"2504.14773","title":"PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities","created":"2025-04-21","cited_by_count":7,"area":"agents"},{"id":"2505.15935","title":"MAPS: A Multilingual Benchmark for Agent Performance and Security","created":"2025-05-21","cited_by_count":7,"area":"agents"},{"id":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","cited_by_count":7,"area":"agents"},{"id":"2606.16748","title":"MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents","created":"2026-06-15","cited_by_count":7,"area":"agents"},{"id":"2607.08938","title":"Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation","created":"2026-07-09","cited_by_count":7,"area":"agents"},{"id":"2607.14651","title":"MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents","created":"2026-07-16","cited_by_count":7,"area":"agents"},{"id":"2608.14380","title":"AgentRewind: Recoverable Execution for Long-Horizon LLM Agents","created":"2026-08-14","cited_by_count":7,"area":"agents"},{"id":"2502.12149","title":"HARBOR: Exploring Persona Dynamics in Multi-Agent Competition","created":"2025-02-17","cited_by_count":6,"area":"agents"},{"id":"2504.01495","title":"Are Autonomous Web Agents Good Testers?","created":"2025-04-02","cited_by_count":6,"area":"agents"},{"id":"2506.04098","title":"TextAtari: 100K Frames Game Playing with Language Agents","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2507.19132","title":"OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?","created":"2025-07-25","cited_by_count":6,"area":"agents"},{"id":"2510.05307","title":"When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2601.18217","title":"Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2604.00073","title":"Terminal Agents Suffice for Enterprise Automation","created":"2026-03-31","cited_by_count":6,"area":"agents"},{"id":"2605.14892","title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2601.09032","title":"The Hierarchy of Agentic Capabilities: Evaluating Frontier Models on Realistic RL Environments","created":"2026-01-13","cited_by_count":5,"area":"agents"},{"id":"2602.02039","title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","created":"2026-02-02","cited_by_count":5,"area":"agents"},{"id":"2606.03103","title":"DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration","created":"2026-06-02","cited_by_count":5,"area":"agents"},{"id":"2608.14036","title":"Demystifying Agent Skills: Why They Work-Until They Don't","created":"2026-08-14","cited_by_count":5,"area":"agents"},{"id":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"area":"agents"},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2510.09801","title":"How can we assess human-agent interactions? Case studies in software agent design","created":"2025-10-10","cited_by_count":4,"area":"agents"},{"id":"2510.19286","title":"TheMCPCompany: Creating General-purpose Agents with Task-specific Tools","created":"2025-10-22","cited_by_count":4,"area":"agents"},{"id":"2603.10268","title":"SpecOps: A Fully Automated AI Agent Testing Framework in Real-World GUI Environments","created":"2026-03-10","cited_by_count":4,"area":"agents"},{"id":"2603.23638","title":"Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2604.10015","title":"FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.30434","title":"LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2607.01084","title":"Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use","created":"2026-07-01","cited_by_count":4,"area":"agents"},{"id":"2505.19764","title":"Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows","created":"2025-05-26","cited_by_count":3,"area":"agents"}],"next_cursor":"100"}